模擬登陸狀態的兩種方法
阿新 • • 發佈：2019-02-19
1.直接登陸後獲取cookie
import requests # 直接將登陸成功之後的Cookie放在headers中，向頁面傳送請求。 url = 'https://www.zhihu.com/' headers = { "Host": "www.zhihu.com", "Referer": "https://www.zhihu.com/signup?next=%2F", "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:60.0) Gecko/20100101 Firefox/60.0", "Cookie": 'd_c0="AGAku45jtw2PTu09Dpvhke4klei4JarodIE=|1528425319"; q_c1=a46ba33124a2403cb907a2d9105a7bd4|1528425319000|1528425319000; capsion_ticket="2|1:0|10:1528705722|14:capsion_ticket|44:NzE1YzNhZmJiZjIxNDA1MTg4ZTdkN2YyMTFiNWQwNTk=|42d9339a55b21206f1cae511940cab2468b6e201c1adce2c958be61edfadb1a0"; _zap=cc087957-a74b-43fc-a1d9-f7bd685897b7; _xsrf=8e9717b7-05a4-481c-8e82-3ca140d5b266; tgw_l7_route=156dfd931a77f9586c0da07030f2df36; z_c0="2|1:0|10:1528705732|4:z_c0|92:Mi4xRHBTMkJRQUFBQUFBWUNTN2ptTzNEU1lBQUFCZ0FsVk54SUFMWEFEMGtfeUowbzNNeXlQRjcwYXVSNV9zMHV1UXZn|27f3bcbcc0b8271658d88009ef05d80b3da8b6df2fb156a7c186a5d076047a63'} # allow_redirects=False 禁止重定向的引數。否則，無法獲取302的狀態碼。 response = requests.get(url, headers=headers, allow_redirects=False) print(response.status_code) # 302 print(response.text)
2.從登陸介面通過抓包的方式獲取訪問了那一些網址,一知乎為例
1>中文驗證碼
# 英文驗證碼的登入方式 # 中文登入（點選倒立文字） import requests,time,json # from requests.packages.urllib3.exceptions import InsecureRequestWarning# requests.packages.urllib3.disable_warnings(InsecureRequestWarning) headers = { "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:60.0) Gecko/20100101 Firefox/60.0", "Referer": "https://www.zhihu.com/signup?next=%2F", "origin": "https://www.zhihu.com", "Authorization": "oauth c3cef7c66a1843f8b3a9e6a1e3160e20", } # cookies的自動化管理。 # 獲取的伺服器的Set-Cookie用session直接自動解析並儲存，在後續的請求中，會在請求頭中自動攜帶這些cookie # LWPCookieJar:對cookie進行自動操作，load() save() from http.cookiejar import LWPCookieJar session = requests.Session() session.cookies = LWPCookieJar(filename='zhihucookie.txt') try: session.cookies.load(filename='zhihucookie.txt', ignore_expires=True, ignore_discard=True) except Exception as e: print('載入失敗') res = session.get('https://www.zhihu.com/', headers=headers, verify=False) print(res) def zhihu_login(): global session cap = '' has_captcha = is_captcha() if has_captcha: # 獲取驗證碼 cap = get_captcha() # 在提交登陸之前，還需要對輸入的驗證碼的正確性進行單獨驗證 is_true = check_captcha(cap) if is_true == False: return # 1528450244046.0112 print(time.time()) login_url = "https://www.zhihu.com/api/v3/oauth/sign_in" post_params = { "client_id":"c3cef7c66a1843f8b3a9e6a1e3160e20", "grant_type": "password", "timestamp": "1528450006722", "source": "com.zhihu.web", "signature": "dbaccdbeeade95fa9ec65ad72f3cdc1473a5a245", "username": "17737713931", "password": "gaohairui521", "captcha": cap, "lang": "cn", "ref_source": "homepage", "utm_source": "", } try: response = session.post(login_url, data=post_params, headers=headers, verify=False) if response.status_code == 201: session.cookies.save(ignore_discard=True, ignore_expires=True) print(response.text) else: print('登陸失敗') except Exception as e: print('請求失敗',e) def is_captcha(): global COOKIE captcha_url = 'https://www.zhihu.com/api/v3/oauth/captcha?lang=cn' try: response = session.get(url=captcha_url, headers=headers,verify=False) if response.status_code == 200: show_captcha = json.loads(response.text)['show_captcha'] if show_captcha: print('有驗證碼') return True else: print('沒有驗證碼') return False except Exception as e: print('') import base64 from PIL import Image from io import BytesIO all_points = [[16.5,25.933349609375],[37.5,16.933349609375],[62.5,21.933349609375],[85.5,21.933349609375],[113.5,25.933349609375],[139.5,19.933349609375],[165.5,20.933349609375]] def get_captcha(): captcha_url = 'https://www.zhihu.com/api/v3/oauth/captcha?lang=cn' # set-cookie: capsion_ticket="2|1:0|10:1528448404|14:capsion_ticket|44:MjIyMTdjMDNlNWQ0NDU4NDk3YWJiYTJhMGNhYzdhMGU=|27fc1b86cbb52d627f270fdc6ee72f58f88ae09b76483d30ff1026418d83bfce"; Domain=zhihu.com; expires=Sun, 08 Jul 2018 09:00:04 GMT; httponly; Path=/ try: # 索取驗證碼圖片，在保證有驗證碼的前提下才會發送PUT response = session.put(url=captcha_url, headers=headers,verify=False) if response.status_code == 202: captcha_url = json.loads(response.text)['img_base64'] # 解碼captcha_url url = base64.b64decode(captcha_url) url = BytesIO(url) image = Image.open(url) image.show() captcha = input('請輸入倒立漢字所在的位置：13') result_captcha = '' # 倒立漢字可能是1個或者2個 if len(captcha) == 1: # 一個倒立漢字 point = all_points[int(captcha)-1] result_captcha = '{"img_size":[200,44], "input_points":[%s]}' % point else: # 兩個倒立漢字 first_char = captcha[0] second_char = captcha[1] first_point = all_points[int(first_char) - 1] second_point = all_points[int(second_char) - 1] result_captcha = '{"img_size":[200,44], "input_points":[%s, %s]}' % (first_point, second_point) return result_captcha except Exception as e: print('') def check_captcha(captcha): captcha_url = 'https://www.zhihu.com/api/v3/oauth/captcha?lang=cn' post_params = { 'input_text': captcha } # verify=False: 在傳送https請求的時候，關閉證書認證 response = session.post(url=captcha_url, data=post_params, headers=headers, verify=False) json_obj = json.loads(response.text) if 'success' in json_obj: print('輸入驗證碼正確') return True else: print('輸入驗證碼不正確') return False if __name__ == '__main__': zhihu_login() # [SSL: CERTIFICATE_VERIFY_FAILED]: 在requests傳送https請求時，出現的證書認證失敗，解決辦法：verify=False # InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings # InsecureRequestWarning)
2>英文驗證碼:
# 英文驗證碼的登入方式 # 中文登入（點選倒立文字） import requests,time,json # from requests.packages.urllib3.exceptions import InsecureRequestWarning # requests.packages.urllib3.disable_warnings(InsecureRequestWarning) headers = { "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:60.0) Gecko/20100101 Firefox/60.0", "Referer": "https://www.zhihu.com/signup?next=%2F", "origin": "https://www.zhihu.com", "Authorization": "oauth c3cef7c66a1843f8b3a9e6a1e3160e20", } # 獲取的伺服器的Set-Cookie用session直接自動解析並儲存，在後續的請求中，會在請求頭中自動攜帶這些cookie # LWPCookieJar:對cookie進行自動操作，load() save() from http.cookiejar import LWPCookieJar session = requests.Session() session.cookies = LWPCookieJar(filename='zhihucookie.txt') try: session.cookies.load(filename='zhihucookie.txt', ignore_expires=True, ignore_discard=True) except Exception as e: print('載入失敗') res = session.get('https://www.zhihu.com/', headers=headers, verify=False) print(res) def zhihu_login(): global session has_captcha = is_captcha() if has_captcha: # 獲取驗證碼 captcha = get_captcha() # 在提交登陸之前，還需要對輸入的驗證碼的正確性進行單獨驗證 is_true = check_captcha(captcha) if is_true == False: return # 1528450244046.0112 print(time.time()) login_url = "https://www.zhihu.com/api/v3/oauth/sign_in" post_params = { "client_id":"c3cef7c66a1843f8b3a9e6a1e3160e20", "grant_type": "password", "timestamp": "1528450006722", "source": "com.zhihu.web", "signature": "dbaccdbeeade95fa9ec65ad72f3cdc1473a5a245", "username": "17737713931", "password": "gaohairui521", "captcha": captcha, "lang": "cn", "ref_source": "homepage", "utm_source": "", } try: response = session.post(login_url, data=post_params, headers=headers, verify=False) if response.status_code == 201: session.cookies.save(ignore_discard=True, ignore_expires=True) print(response.text) else: print('登陸失敗') except Exception as e: print('請求失敗',e) def is_captcha(): global COOKIE captcha_url = 'https://www.zhihu.com/api/v3/oauth/captcha?lang=en' try: response = session.get(url=captcha_url, headers=headers,verify=False) if response.status_code == 200: show_captcha = json.loads(response.text)['show_captcha'] if show_captcha: print('有驗證碼') return True else: print('沒有驗證碼') return False except Exception as e: print('') import base64 from PIL import Image from io import BytesIO def get_captcha(): captcha_url = 'https://www.zhihu.com/api/v3/oauth/captcha?lang=en' # set-cookie: capsion_ticket="2|1:0|10:1528448404|14:capsion_ticket|44:MjIyMTdjMDNlNWQ0NDU4NDk3YWJiYTJhMGNhYzdhMGU=|27fc1b86cbb52d627f270fdc6ee72f58f88ae09b76483d30ff1026418d83bfce"; Domain=zhihu.com; expires=Sun, 08 Jul 2018 09:00:04 GMT; httponly; Path=/ try: # 索取驗證碼圖片，在保證有驗證碼的前提下才會發送PUT response = session.put(url=captcha_url, headers=headers,verify=False) if response.status_code == 202: captcha_url = json.loads(response.text)['img_base64'] # 解碼captcha_url url = base64.b64decode(captcha_url) url = BytesIO(url) image = Image.open(url) image.show() captcha = input('請輸入驗證碼：') return captcha except Exception as e: print('') def check_captcha(captcha): captcha_url = 'https://www.zhihu.com/api/v3/oauth/captcha?lang=en' post_params = { 'input_text': captcha } # verify=False: 在傳送https請求的時候，關閉證書認證 response = session.post(url=captcha_url, data=post_params, headers=headers, verify=False) json_obj = json.loads(response.text) if 'success' in json_obj: print('輸入驗證碼正確') return True else: print('輸入驗證碼不正確') return False # if __name__ == '__main__': # zhihu_login() # [SSL: CERTIFICATE_VERIFY_FAILED]: 在requests傳送https請求時，出現的證書認證失敗，解決辦法：verify=False # InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings # InsecureRequestWarning)